Harmonization of Structural Brain Connectivity Through Distribution Matching

Abstract

The increasing prevalence of multi-site diffusion-weighted magnetic resonance imaging (dMRI) studies potentially offers enhanced statistical power to investigate brain structure. However, these studies face challenges due to variations in scanner hardware and acquisition protocols. While several methods for dMRI data harmonization exist, few specifically address structural brain connectivity. We introduce a new distribution-matching approach to harmonizing structural brain connectivity across different sites and scanners. We evaluate our method using structural brain connectivity data from three distinct datasets (OASIS-3, ADNI-2, and PREVENT-AD), comparing its performance to the widely used ComBat method and the more recent CovBat approach. We examine the impact of harmonization on the correlation of brain connectivity with the Mini-Mental State Examination score and age. Our results demonstrate that our distribution-matching technique effectively harmonizes structural brain connectivity while maintaining non-negativity of the connectivity values and produces correlation strengths and significance levels competitive with alternative approaches. Qualitative assessments illustrate the desired distributional alignment across datasets, while quantitative evaluations confirm competitive performance. This work contributes to the growing field of dMRI harmonization, potentially improving the reliability and comparability of structural connectivity studies that combine data from different sources in neuroscientific and clinical research.

Keywords: connectome; diffusion MRI; distribution matching; harmonization; structural brain connectivity.

FIGURE 1

Normalized histograms of five connectivity values selected by choosing the smallest, 25th percentile, median, 75th percentile, and largest improvement in significance values ($\mathrm{\Delta }s$) from the correlation between MMSE and brain connectivity. Each column represents a structural brain connection, with the first row showing the reference OASIS‐3 data and the second row representing the ADNI‐2 data before harmonization. The third, fourth, and fifth rows show ADNI‐2 data after harmonization using the DM, ComBat, and CovBat methods (all without including covariates), respectively. The red curves show the fitted gamma distribution for OASIS‐3, as well as for ADNI‐2 before and after DM harmonization. ComBat and CovBat harmonized data display more irregular, multimodal distributions, with some zero values transformed to non‐zero values. We projected the negative values produced by ComBat and CovBat to zero for visualization consistency.

FIGURE 2

The histogram of $s≔-\log p$ from Pearson's correlation between original (a,c) or augmented (b,d) structural brain connectivity and MMSE (a,b) or age (c,d), before and after harmonization. The red dashed vertical line represents the significance cutoff threshold of $-\log 0.05$.

FIGURE 3

Scatter plots comparing post‐ vs. pre‐harmonization Pearson's correlation ($r$) between MMSE (top) or age (bottom) and original (left) or augmented (right) structural brain connectivity. The identity line is plotted in red. In all cases, the proposed DM harmonization increased the overall $\mid r\mid$.

FIGURE 4

Distribution of the PDFs of the brain connection most correlated with (a) age and (b) MMSE. Each plot compares 1000 random permutations to select a subset of 106 subjects (red curves), to the full dataset with 209 subjects (blue curve), in ADNI‐2. The brain connection most correlated with age (a) is between the left thalamus and left hippocampus. The connection most correlated with MMSE (b) is between the left lingual cortex and left middle temporal cortex.